#SounDoer# Introduction to Artificial Intelligence in Music Composition

@SounDoer:Introduction to Artificial Intelligence in Music Composition,搬运了一些资料。
 
云盘链接:
密码: vae1
 
My Opinion:
  • The quality of music composition mostly depends on the learning materials that are fed the AI system with.
  • The advantage of AI composition system is creating many variations in a short time, but the results may not be as delicate as human composers.
  • Composition is just one step in music production. The whole quality of music work is related with many other elements which AI composition system needs to make further efforts on.
  • From the standpoint of practicability, the AI composition systems mentioned before may only works for single-mood background music in short videos currently.
  • The AI composition system is not capable of film/game scoring independently at present as film/game music demands much more details. For example, it is not easy for AI system to detect emotions from visual.
  • For human composers, AI composition system can be a useful tool to get new and unexpected ideas.
  • Composer will not die out… for a while!
Illiac Suite
The Illiac Suite is the first musical composition for traditional instruments that was made through computer-assisted composition by Lejaren Hiller and Leonard Isaacson.
According to Hiller, music could be defined as a sensible form governed by laws of organization that could be encoded in ways quite accurate.
“Music is a sensible form. It is governed by laws of organization which permit fairly exact codification.”
“The process of musical composition can be characterized as involving a series of choices of musical elements from an essentially limitless variety of musical raw materials.”
 
Lejaren Hiller – Illiac Suite for String Quartet [1/4]
Lejaren Hiller – Illiac Suite for String Quartet [2/4]
Lejaren Hiller – Illiac Suite for String Quartet [3/4]
Lejaren Hiller – Illiac Suite for String Quartet [4/4]
 
Flow Machines by Sony CSL
Flow machines is a research project funded by the European Research Council (ERC) and coordinated by François Pachet. Flow machines addresses the issue of enhancing individual creativity by looking at it through the concept of “reflexive interactions”. Reflexive Interactions are human-machine interactions with a system that attempts to imitate the user’s style. The vision behind flow machines is that manipulating images of oneself creates novel and very effective ways to boost creativity. This was demonstrated in particular with the Continuator system, and with interactions with jazz professionals, as well as children (see also the ongoing Miror project). The flow machines project will push these ideas further by proposing a radically new way of looking at content creation tools.
 
DeepBach: harmonization in the style of Bach generated using deep learning
This piece is a harmonization generated using DeepBach, a deep learning tool for automatic generation of chorales in Bach’s style, in the framework of the ERC-funded Flow Machines project led by François Pachet.
DeepBach is developed by Gaëtan Hadjeres, Sony CSL and LIP6 (UPMC/CNRS).
Performed by Emmanuel Deruty using Küng recorders
Flow Machines project is funded by the European Research Council under the Seventh Framework Programme / ERC Grant Agreement n. 291156
 
Daddy’s Car: a song composed by Artificial Intelligence – in the style of the Beatles
Scientists at SONY CSL Research Lab have created the first-ever entire songs composed by Artificial Intelligence: “Daddy’s Car” and “Mister Shadow”.
The researchers have developed FlowMachines, a system that learns music styles from a huge database of songs. Exploiting unique combinations of style transfer, optimization and interaction techniques, FlowMachines composes novel songs in many styles.
“Daddy’s Car” is composed in the style of The Beatles. French composer Benoît Carré arranged and produced the songs, and wrote the lyrics.
The two songs are excerpts of albums composed by Artificial Intelligence to be released in 2017.
The research behind Daddy’s Car is financed by the ERC grant “Flow Machines”, Flow Machines is a project leaded by François Pachet and hosted by the Parisian University Pierre and Marie Curie.
 
Mr Shadow: a song composed by Artificial Intelligence
Scientists at SONY CSL Research Laboratory have created the first-ever entire songs composed by Artificial Intelligence: “Daddy’s Car” and “Mister Shadow”.
The researchers have developed FlowMachines, a system that learns music styles from a huge database of songs. Exploiting unique combinations of style transfer, optimization and interaction techniques, FlowMachines composes novel songs in many styles.
“Mister Shadow” is composed in the style of American songwriters such as Irving Berlin, Duke Ellington, George Gershwin and Cole Porter. French composer Benoît Carré arranged and produced the songs, and wrote the lyrics.
The two songs are excerpts of albums composed by Artificial Intelligence to be released in 2017.
 
FLOWCOMPOSER: COMPOSING WITH AI
Generation of Lead Sheets with FlowComposer
 
Magenta
Magenta is a Google Brain project to ask and answer the questions, “Can we use machine learning to create compelling art and music? If so, how? If not, why not?” Our work is done in TensorFlow, and we regularly release our models and tools in open source. These are accompanied by demos, tutorial blog postings and technical papers. To follow our progress, watch our GitHub and join our discussion group.
Magenta encompasses two goals. It’s first a research project to advance the state-of-the art in music, video, image and text generation. So much has been done with machine learning to understand content—for example speech recognition and translation; in this project we explore content generation and creativity. Second, Magenta is building a community of artists, coders, and machine learning researchers. To facilitate that, the core Magenta team is building open-source infrastructure around TensorFlow for making art and music. This already includes tools for working with data formats like MIDI, and is expanding to platforms that help artists connect with machine learning models.
 
Magenta AI Jam Session
This is an interactive demo featuring drums, piano, and bass generated by LSTMs in response to real-time user input. More information at https://magenta.tensorflow.org/2016/12/16/nips-demo
 
NSynth Ableton Live Instrument
Neural Audio Synthesis
 
Magenta: Music and Art Generation (TensorFlow Dev Summit 2017)
Using TensorFlow for Music and Art Generation — that’s what Magenta is all about. Join Douglas Eck discusses art and music generation with deep nets and reinforcement learning. He also talks about how artists and musicians fit in to the effort. Be prepared to see and hear inspired ML models.
 
Aiva
 
AIVA – “Genesis” Symphonic Fantasy in A minor, Op. 21
 
Jukedeck
 
Amper Music
 
 
SounDoer– Focus On Sound Design
@SounDoer编译,若有错误还望不吝指教。转载烦请告知并注明出处。